Precise_listen exception


#1

Hi,

After training my model with precise-train I got following exception in precise_listen

(.venv) root@jglozma-HP-ZBook-17-G5:~/mycroft-precise# precise-listen hey-optum.net
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_qint8 = np.dtype([(“qint8”, np.int8, 1)])
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_quint8 = np.dtype([(“quint8”, np.uint8, 1)])
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_qint16 = np.dtype([(“qint16”, np.int16, 1)])
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_quint16 = np.dtype([(“quint16”, np.uint16, 1)])
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_qint32 = np.dtype([(“qint32”, np.int32, 1)])
/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or ‘1type’ as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / ‘(1,)type’.
_ np_resource = np.dtype([(“resource”, np.ubyte, 1)])_
Using TensorFlow backend.
WARNING:tensorflow:From /root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/ops/resource_variable_ops.py:435: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map
Exception in thread Thread-1:
Traceback (most recent call last):
_ File “/usr/local/lib/python3.5/threading.py”, line 914, in bootstrap_inner
_ self.run()_
_ File “/usr/local/lib/python3.5/threading.py”, line 862, in run_
_ self.target(*self.args, **self.kwargs)
_ File “/root/mycroft-precise/runner/precise_runner/runner.py”, line 236, in handle_predictions
_ prob = self.engine.get_prediction(chunk)

_ File “/root/mycroft-precise/precise/scripts/listen.py”, line 87, in get_prediction

_ return listener.update(chunk)_
_ File “/root/mycroft-precise/precise/network_runner.py”, line 139, in update_
_ raw_output = self.runner.run(mfccs)_
_ File “/root/mycroft-precise/precise/network_runner.py”, line 82, in run_
_ return self.predict(inp[np.newaxis])[0][0]_
_ File “/root/mycroft-precise/precise/network_runner.py”, line 79, in predict_
_ return self.model.predict(inputs)_
_ File “/root/mycroft-precise/.venv/lib/python3.5/site-packages/keras/engine/training.py”, line 1462, in predict_
_ callbacks=callbacks)_
_ File “/root/mycroft-precise/.venv/lib/python3.5/site-packages/keras/engine/training_arrays.py”, line 324, in predict_loop_
_ batch_outs = f(ins_batch)_
_ File “/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/keras/backend.py”, line 3076, in call_
_ run_metadata=self.run_metadata)_
_ File “/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/client/session.py”, line 1439, in call_
_ run_metadata_ptr)_
_ File “/root/mycroft-precise/.venv/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py”, line 528, in exit_
_ c_api.TF_GetCode(self.status.status))_
tensorflow.python.framework.errors_impl.FailedPreconditionError: Error while reading resource variable dense_1/bias from Container: localhost. This could mean that the variable was uninitialized. Not found: Container localhost does not exist. (Could not find resource: localhost/dense_1/bias)
_ [[{{node dense_1/BiasAdd/ReadVariableOp}}]]_

Could somebody, please, help?
Thank you


#2

I’m getting the same exception trying to test my model, and I get an exception when trying to convert the model using precise-convert.


#3

Same error with precise-listen.